pdf

Processes PDFs with text/table extraction, merging, splitting, rotation, OCR, and form filling.

Updated Aug 27, 2026

Search Tags:#automation #pdf #forms #document-processing #data-extraction #text-extraction

Ready to run

npx skills add https://github.com/HTRamsey/claude-config --skill pdf-htramsey

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/HTRamsey/claude-config/tree/main/skills/pdf
Command: npx skills add https://github.com/HTRamsey/claude-config --skill pdf-htramsey

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pytesseract, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Core Features & Use Cases

Text extraction, table extraction, and page rotation
PDF merging, splitting, and page-level operations
Form filling, OCR, and advanced formatting

Quick Start

Demonstrates basic PDF operations using Python libraries (pypdf, pdfplumber, reportlab) and CLI tools.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text and tables from PDF documents programmatically?▼

Text and table extraction from PDFs uses libraries like pdfplumber and pypdf to parse document content. pdfplumber specializes in structured table extraction, while pypdf handles text across pages, supporting both native PDFs and scanned documents with OCR via pytesseract.

Can I automate PDF form filling and field population?▼

Yes, pypdf enables programmatic form field detection and population. The Skill includes scripts for field extraction and form filling, allowing batch automation of PDF forms without manual entry or external tools.

What's the best way to merge, split, and rotate PDF pages at scale?▼

pypdf and reportlab provide page-level operations for merging documents, splitting by range, and rotating pages. These operations scale to batch workflows, making it practical for processing hundreds of documents programmatically.

How do I handle OCR and extract text from scanned PDF images?▼

Scanned PDFs require OCR processing via pytesseract with poppler utilities and pdf2image for page rendering. The Skill automates OCR workflows, converting image-based pages to searchable text for extraction and indexing.

Can I create new PDFs and add watermarks or annotations programmatically?▼

reportlab creates PDFs from scratch with custom layouts and content. The Skill supports watermarking and annotation through pypdf and reportlab, enabling document generation and markup in automated workflows.

What Python libraries do I need for comprehensive PDF processing?▼

Core libraries are pypdf, pdfplumber, and reportlab for manipulation and creation. Optional dependencies include pytesseract for OCR and pdf2image for rendering, with CLI tools like pdftotext, qpdf, and pdftk for supplementary operations.